An Efficient Human Activity Recognition Technique Based on Deep Learning
Article dans une revue avec comité de lecture
Date
2019Journal
Распознавание образов и анализ изображен / Pattern Recognition and Image Analysis: Advances in Mathematical Theory and ApplicationsRésumé
In this paper, we present a new deep learning-based human activity recognition technique. First, we track and extract human body from each frame of the video stream. Next, we abstract human silhouettes and use them to create binary space-time maps (BSTMs) which summarize human activity within a defined time interval. Finally, we use convolutional neural network (CNN) to extract features from BSTMs and classify the activities. To evaluate our approach, we carried out several tests using three public datasets: Weizmann, Keck Gesture and KTH Database. Experimental results show that our technique outperforms conventional state-of-the-art methods in term of recognition accuracy and provides comparable performance against recent deep learning techniques. It’s simple to implement, requires less computing power, and can be used for multi-subject activity recognition.
Fichier(s) constituant cette publication
Cette publication figure dans le(s) laboratoire(s) suivant(s)
Documents liés
Visualiser des documents liés par titre, auteur, créateur et sujet.
-
Article dans une revue avec comité de lectureRABAH, Souad; ASSILA, Ahlem; KHOURI, Elio; MAIER, Florian; ABABSA, Fakhreddine; BOURNY, Valéry; MAIER, Paul; MERIENNE, Frédéric (Elsevier, 2018)We are on the cusp of a technological revolution that will fundamentally change our relationships to others and the way we live and work. These changes, in their importance, scope, and complexity, is different than what ...
-
Communication avec acteIn augmented reality environments, the natural hand interaction between a virtual object and the user is a major issue to manipulate a rendered object in a convenient way. Microsoft’s HoloLens (Microsoft 2018) is an ...
-
Communication avec acteFISCHINI, Antoine; ABABSA, Fakhreddine; GRASSER, Mickaël (2018)Augmented Reality (AR) is a strong growing research topic in several areas including industry, training, art and entertainment. AR can help users to achieve very complex tasks by enhancing their vision with useful and ...
-
Communication avec acteABABSA, Fakhreddine; HADJ-ABDELKADER, Hicham; BOUI, Marouane (ACM Press, 2019)This paper deals with the problem of 3D human tracking in catadioptric images using particle-filtering framework. While traditional perspective images are well exploited, only a few methods have been developed for catadioptric ...
-
Communication avec actePRUVOST, Martin; MIALOCQ, Pierre; ABABSA, Fakhreddine (2018)This paper presents an AR system architecture for assisting complex assembly work by adding visual information superimposed on the physical assembly parts.